{"id":"W2114960120","doi":"","title":"Stochastic Ratio Matching of RBMs for Sparse High-Dimensional Inputs","year":2013,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Bottleneck; Encoder; Estimator; Feature (linguistics); Algorithm; Matching (statistics); Feature vector; Sampling (signal processing); Feature matching; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003124652,0.0001294435,0.0001876405,0.0001771518,0.0002185686,0.0006134624,0.0003023179,0.00005869211,0.000005951295],"category_scores_gemma":[0.0000907881,0.0001129487,0.00004188515,0.0002413211,0.00002853581,0.005080482,0.00005666818,0.0001017047,0.00005973609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003328384,"about_ca_system_score_gemma":0.0001122893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004429453,"about_ca_topic_score_gemma":5.835271e-7,"domain_scores_codex":[0.9985924,0.000033775,0.0006571658,0.0001317788,0.0003767881,0.0002081018],"domain_scores_gemma":[0.9986002,0.00008341062,0.0005844324,0.0001717785,0.0004847033,0.00007544141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000914469,0.00001637631,0.00001157044,0.0003708581,0.000007732143,1.37101e-7,0.003917211,0.9321606,0.002254243,0.0228271,0.0007055775,0.03771949],"study_design_scores_gemma":[0.0003915732,0.0000407379,0.0001664693,0.0001037839,0.000003286898,0.00001276663,0.0001590771,0.997908,0.0002302648,0.0006650397,0.0001920992,0.0001268804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03584966,0.00003442636,0.9623456,0.0003875298,0.000482407,0.0005227207,0.000003059188,0.0001519848,0.0002226045],"genre_scores_gemma":[0.9794368,1.849831e-7,0.01970432,0.0004850907,0.00004479522,0.0001085559,0.00002466495,0.000006924693,0.0001887319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9435871,"threshold_uncertainty_score":0.5915632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0189065197988435,"score_gpt":0.2398642829548209,"score_spread":0.2209577631559774,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}